3D Adversarial Attacks Beyond Point Cloud
- URL: http://arxiv.org/abs/2104.12146v1
- Date: Sun, 25 Apr 2021 13:01:41 GMT
- Title: 3D Adversarial Attacks Beyond Point Cloud
- Authors: Jinlai Zhang, Lyujie Chen, Binbin Liu, Bo Ouyang, Qizhi Xie, Jihong
Zhu, Yanmei Meng
- Abstract summary: Previous adversarial attacks on 3D point clouds mainly focus on add perturbation to the original point cloud.
We present a novel adversarial attack, named Mesh Attack, to address this problem.
- Score: 8.076067288723133
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Previous adversarial attacks on 3D point clouds mainly focus on add
perturbation to the original point cloud, but the generated adversarial point
cloud example does not strictly represent a 3D object in the physical world and
has lower transferability or easily defend by the simple SRS/SOR. In this
paper, we present a novel adversarial attack, named Mesh Attack to address this
problem. Specifically, we perform perturbation on the mesh instead of point
clouds and obtain the adversarial mesh examples and point cloud examples
simultaneously. To generate adversarial examples, we use a differential sample
module that back-propagates the loss of point cloud classifier to the mesh
vertices and a mesh loss that regularizes the mesh to be smooth. Extensive
experiments demonstrated that the proposed scheme outperforms the SOTA attack
methods. Our code is available at:
{\footnotesize{\url{https://github.com/cuge1995/Mesh-Attack}}}.
Related papers
- epsilon-Mesh Attack: A Surface-based Adversarial Point Cloud Attack for
Facial Expression Recognition [0.8192907805418583]
A common method is to use adversarial attacks where the gradient direction is followed to change the input slightly.
In this paper, we suggest an adversarial attack called $epsilon$-Mesh Attack, which operates on point cloud data via limiting perturbations to be on the mesh surface.
Our method successfully confuses trained DGCNN and PointNet models $99.72%$ and $97.06%$ of the time, with indistinguishable facial deformations.
arXiv Detail & Related papers (2024-03-11T12:29:55Z) - PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models
Against Adversarial Examples [63.84378007819262]
We propose PointCA, the first adversarial attack against 3D point cloud completion models.
PointCA can generate adversarial point clouds that maintain high similarity with the original ones.
We show that PointCA can cause a performance degradation from 77.9% to 16.7%, with the structure chamfer distance kept below 0.01.
arXiv Detail & Related papers (2022-11-22T14:15:41Z) - Shape-invariant 3D Adversarial Point Clouds [111.72163188681807]
Adversary and invisibility are two fundamental but conflict characters of adversarial perturbations.
Previous adversarial attacks on 3D point cloud recognition have often been criticized for their noticeable point outliers.
We propose a novel Point-Cloud Sensitivity Map to boost both the efficiency and imperceptibility of point perturbations.
arXiv Detail & Related papers (2022-03-08T12:21:35Z) - Boosting 3D Adversarial Attacks with Attacking On Frequency [6.577812580043734]
We propose a novel point cloud attack (dubbed AOF) that pays more attention on the low-frequency component of point clouds.
Experiments validate that AOF can improve the transferability significantly compared to state-of-the-art (SOTA) attacks.
arXiv Detail & Related papers (2022-01-26T13:52:17Z) - Geometric Adversarial Attacks and Defenses on 3D Point Clouds [25.760935151452063]
In this work, we explore adversarial examples at a geometric level.
That is, a small change to a clean source point cloud leads, after passing through an autoencoder model, to a shape from a different target class.
On the defense side, we show that remnants of the attack's target shape are still present at the reconstructed output after applying the defense to the adversarial input.
arXiv Detail & Related papers (2020-12-10T13:30:06Z) - LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of
Point Cloud-based Deep Networks [123.5839352227726]
This paper proposes a novel label guided adversarial network (LG-GAN) for real-time flexible targeted point cloud attack.
To the best of our knowledge, this is the first generation based 3D point cloud attack method.
arXiv Detail & Related papers (2020-11-01T17:17:10Z) - IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function
based Restoration [68.88711148515682]
Deep neural networks are vulnerable to various 3D adversarial attacks.
We propose an IF-Defense framework to directly optimize the coordinates of input points with geometry-aware and distribution-aware constraints.
Our results show that IF-Defense achieves the state-of-the-art defense performance against existing 3D adversarial attacks on PointNet, PointNet++, DGCNN, PointConv and RS-CNN.
arXiv Detail & Related papers (2020-10-11T15:36:40Z) - GRNet: Gridding Residual Network for Dense Point Cloud Completion [54.43648460932248]
Estimating the complete 3D point cloud from an incomplete one is a key problem in many vision and robotics applications.
We propose a novel Gridding Residual Network (GRNet) for point cloud completion.
Experimental results indicate that the proposed GRNet performs favorably against state-of-the-art methods on the ShapeNet, Completion3D, and KITTI benchmarks.
arXiv Detail & Related papers (2020-06-06T02:46:39Z) - ShapeAdv: Generating Shape-Aware Adversarial 3D Point Clouds [78.25501874120489]
We develop shape-aware adversarial 3D point cloud attacks by leveraging the learned latent space of a point cloud auto-encoder.
Different from prior works, the resulting adversarial 3D point clouds reflect the shape variations in the 3D point cloud space while still being close to the original one.
arXiv Detail & Related papers (2020-05-24T00:03:27Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.